Keras metadata
Get metadata about a trained Keras block. Use the impulse blocks to find the learnId.
Authorizations
Path parameters
projectIdintegerRequired
Project ID
learnIdintegerRequired
Learn Block ID, use the impulse functions to retrieve the ID
Query parameters
excludeLabelsbooleanOptional
If set to "true", the "labels" field is left empty (which can be big on e.g. regression projects).
Responses
200
OK
application/json
Responseall of
get
GET /v1/api/{projectId}/training/keras/{learnId}/metadata HTTP/1.1
Host: studio.edgeimpulse.com
x-api-key: YOUR_API_KEY
Accept: */*
200
OK
{
"success": true,
"error": "text",
"created": "2025-06-30T22:10:26.293Z",
"layers": [
{
"input": {
"shape": 33,
"name": "x_input:0",
"type": "<dtype: 'float32'>"
},
"output": {
"shape": 20,
"name": "dense_1/Relu:0",
"type": "<dtype: 'float32'>"
}
}
],
"classNames": [
"text"
],
"labels": [
"text"
],
"availableModelTypes": [
"int8"
],
"recommendedModelType": "int8",
"modelValidationMetrics": [
{
"type": "int8",
"loss": 1,
"accuracy": 1,
"confusionMatrix": [
[
31,
1,
0
],
[
2,
27,
3
],
[
1,
0,
39
]
],
"report": {},
"onDevicePerformance": [
{
"mcu": "text",
"name": "text",
"isDefault": true,
"latency": 1,
"tflite": {
"ramRequired": 1,
"romRequired": 1,
"arenaSize": 1,
"modelSize": 1
},
"eon": {
"ramRequired": 1,
"romRequired": 1,
"arenaSize": 1,
"modelSize": 1
},
"eon_ram_optimized": {
"ramRequired": 1,
"romRequired": 1,
"arenaSize": 1,
"modelSize": 1
},
"customMetrics": [
{
"name": "text",
"value": "text"
}
],
"hasPerformance": true,
"profilingError": "text"
}
],
"predictions": [
{
"sampleId": 1,
"startMs": 1,
"endMs": 1,
"label": "text",
"prediction": "text",
"predictionCorrect": true,
"f1Score": 1,
"anomalyScores": [
[
1
]
]
}
],
"visualization": "featureExplorer",
"isSupportedOnMcu": true,
"mcuSupportError": "text",
"profilingJobId": 1,
"profilingJobFailed": true,
"additionalMetrics": [
{
"name": "text",
"value": "text",
"fullPrecisionValue": 1,
"tooltipText": "text",
"link": "text"
}
]
}
],
"hasTrainedModel": true,
"mode": "classification",
"objectDetectionLastLayer": "mobilenet-ssd",
"imageInputScaling": "0..1",
"thresholds": [
{
"key": "min_score",
"description": "Score threshold",
"helpText": "Threshold score for bounding boxes. If the score for a bounding box is below this the box will be discarded.",
"suggestedValue": 1,
"suggestedValueText": "text",
"value": 0.5
}
],
"tensorboardGraphs": [
{
"title": "text",
"xLabel": "text",
"yLabel": "text",
"description": "text",
"hideInUI": true,
"data": [
{
"title": "text",
"values": [
1
]
}
]
}
]
}
Last updated
Was this helpful?